Never stop coding. Free MIT AI gateway: one endpoint, 290+ providers (90+ free), 500+ models — Kimi, Claude, GPT, OpenAI, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 500+ contributors
OmniRoute is a TypeScript-based AI gateway that exposes a single OpenAI-compatible endpoint and routes requests across 177 model providers, more than 50 of which offer free inference tiers. Developers point Claude Code, Cursor, Cline, Copilot, Codex, and Gemini CLI at that endpoint without changing their existing tool configurations, and OmniRoute handles provider selection, load balancing across 14 routing strategies, and automatic fallback when a provider hits rate limits or goes down. Two built-in compression techniques, RTK and Caveman, strip tokens from prompts before they leave the client, with the project claiming reductions of 15 to 95 percent depending on content type. The gateway also exposes MCP and Agent-to-Agent (A2A) interfaces, making it usable inside Claude Desktop and multi-agent workflows. A standout figure from the README is the aggregated free tier capacity of roughly 1.9 billion tokens per month, rising to about 2.5 billion during an initial signup period. The project targets developers and coding-agent users who want to avoid rate limits and API costs without migrating to new tooling.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/diegosouzapw/OmniRoute && cp OmniRoute/*.md ~/.claude/agents/24 items in this repository
Interact with the OmniRoute A2A server from the CLI. Send tasks, inspect skill execution history, and test the JSON-RPC 2.0 agent-to-agent protocol interactively.
Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.
Submit and monitor batch inference jobs from the CLI. Upload and manage files for batch processing, retrieve results, and integrate batch pipelines with CI/CD workflows.
Send chat completions, stream responses, and start an interactive REPL session from the CLI. Supports all OmniRoute providers, combo routing, and system prompt configuration.
Configure and test prompt compression from the CLI. Manage RTK filters, Caveman rules, stacked compression modes, and preview compression output with real prompts.
Manage context engineering configurations, RTK filter sets, and conversation sessions from the CLI. Apply context-relay settings and inspect active context pipelines.
View cost breakdowns, token usage, and call logs from the CLI. Filter by provider, model, or date range. Export usage reports and inspect per-connection spending.
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
Check server health, component status, and live metrics from the CLI. Run `health`, `health components`, and `health watch` for a real-time dashboard of circuit breakers and provider status.
Create, list, rotate, and revoke OmniRoute API keys from the CLI. Manage OAuth flows for provider authentication and inspect key scopes and expiration.
Inspect the MCP server status, list registered tools and scopes, run tool invocations, and manage MCP audit logs from the CLI.
Query available AI models, list model aliases, and browse the full model catalog from the CLI. Filter by provider, search by capability, and resolve model name variants.
Manage Omni Skills (list, install, test, remove), plugins (create, configure), and persistent memory (search, add, clear) from the CLI.
Inspect audit logs, manage access policies, view telemetry data, and review request history from the CLI. Filter by event type, user, or time range for compliance workflows.
Manage provider connections from the CLI: list available/configured providers, add, test, test-all, validate, rotate API keys, and view per-provider metrics.
Inspect and manage circuit-breaker states, connection cooldowns, quota limits, and backoff levels from the CLI. Reset stuck providers and configure resilience thresholds.
Create, list, update, and delete routing combos from the CLI. Test routing strategies, inspect combo metrics, and configure fallback chains interactively.
Start, stop, and restart the OmniRoute server from the CLI. Manage daemon mode, port configuration, auto-recovery, system tray integration, and the dashboard open shortcut.
Run initial setup, configure global CLI settings, manage environment variables, check for updates, and configure autostart via the CLI setup and config commands.
Start and stop tunnel connections (ngrok, Cloudflare, custom) from the CLI. Inspect active tunnel URLs, configure authentication, and test external reachability.
Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use OmniRoute as backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.
Interact with OmniRoute via JSON-RPC 2.0 agent-to-agent protocol. 6 built-in A2A skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities.
Create, list, rotate, and revoke OmniRoute API keys. Control per-key scopes, spending limits, and expiration. Keys gate access to all proxy and management endpoints.
Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the OmniRoute API.
Subagents overview
<div align="center">
<img src="./docs/screenshots/MainOmniRoute.png" alt="OmniRoute Dashboard" width="820"/>
<br/>
<br/>
# 🚀 OmniRoute — The Free AI Gateway
<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 290 providers — 90+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 290 AI providers · 90+ free tiers · ~1.53B free tokens/mo · 19 routing strategies · $0 to start."/>
</div>
<div align="center">
## 💰 ~1.53B Free Tokens / Month
</div>
> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute aggregates the **documented** free tiers of **43 provider pools / 516 models** into one honest number and shows it live on the dashboard (`/dashboard/free-tiers`).
<img src="./docs/diagrams/free-tier-budget.svg" width="100%" alt="OmniRoute free-tier budget card: ~1.53B free tokens per month steady, up to ~2.15B in the first month with signup credits, from the documented free tiers of 43 provider pools / 516 models behind one endpoint. Honest pool-deduped math — each shared pool counted once (counting every rate limit 24/7 would read ~10B; not published), 15 providers ToS-flagged so you decide. Budget bar of the countable free pools with per-model grid (Mistral Large 3 1B, GPT-4o mini 150M, Gemini 2.5 Flash 60M … Claude Sonnet 4.5 25K), one-time first-month signup credits (vertex 300M, agentrouter 200M, predibase 25M, together 25M, glm-cn 20M, doubao 15M, ai21 10M, longcat 10M, deepseek 5M, hyperbolic 5M, nscale 5M), plus permanently-free no-token-cap providers (SiliconFlow, Z.AI GLM-Flash, Kilo, OpenCode Zen, baidu …) and a $10 OpenRouter top-up unlocking +24M/mo — surfaced separately so they never inflate the headline. Live used/remaining on /dashboard/free-tiers."/>
> Animated summary of the live `/dashboard/free-tiers` page. Full methodology (pool dedupe, credit tiers, provider terms): **[docs/reference/FREE_TIERS.md](docs/reference/FREE_TIERS.md)**.
>
> <sub>These figures are re-audited every two weeks against the live catalog and **move both ways** — a provider ends a free tier and the number drops; a new one lands and it climbs. We publish what the catalog actually computes, never a rounded-up best case.</sub>
<br/>
<div align="center">
<h3>
⭐ Star the repo if OMNIROUTE helped you save money and make your work easier.
</h3>
[](https://github.com/diegosouzapw/OmniRoute)
<a href="https://trendshift.io/repositories/23589" target="_blank"><img src="https://trendshift.io/api/badge/repositories/23589" alt="diegosouzapw%2FOmniRoute | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
[](https://www.star-history.com/diegosouzapw/omniroute)
### 💬 Join the community
**👋 Follow the maintainer — get new providers, releases & tips first:**
[](https://www.linkedin.com/in/diegosouzapw/)
[](https://github.com/diegosouzapw)
[](https://discord.gg/U47eFqAXCn)
[](https://t.me/omnirouteOficial)
[](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
[](https://chat.whatsapp.com/LTSpdFhXTxjH4R6CCNiKWz)
[](https://omniroute.online)
**Questions, provider tips, roadmap & support → [Discord](https://discord.gg/U47eFqAXCn) · [Telegram](https://t.me/omnirouteOficial) · WhatsApp [🌍 Global](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) / [🇧🇷 Brasil](https://chat.whatsapp.com/LTSpdFhXTxjH4R6CCNiKWz)**
<br/>
## 🧩 Available
[](https://www.npmjs.com/package/omniroute)
[](https://hub.docker.com/r/diegosouzapw/omniroute)
[](LICENSE)
<table>
<tr>
<td align="center"><a href="#-quick-start"><b>🚀 Quick Start</b></a></td>
<td align="center"><a href="#-combos--the-flagship"><b>🎯 Combos</b></a></td>
<td align="center"><a href="#-290-ai-providers--90-free"><b>🌐 Providers</b></a></td>
</tr>
<tr>
<td align="center"><a href="#-full-cli--a2a--mcp"><b>🔌 CLI & MCP</b></a></td>
<td align="center"><a href="#%EF%B8%8F-save-1595-tokens--automatically"><b>🗜️ Compression</b></a></td>
<td align="center"><a href="https://omniroute.online"><b>🌍 Website</b></a></td>
</tr>
</table>
<table>
<tr>
<td align="center"><a href="#-the-promise">💥 The Promise</a></td>
<td align="center"><a href="#-why-omniroute">🤔 Why</a></td>
<td align="center"><a href="#-what-sets-omniroute-apart">🏆 What Sets Apart</a></td>
</tr>
<tr>
<td align="center"><a href="#-compatible-clis--coding-agents">🤖 Compatible CLIs</a></td>
<td align="center"><a href="#%EF%B8%8F-where-omniroute-runs--anywhere">🖥️ Where It Runs</a></td>
<td align="center"><a href="#-private--local-first">🔒 Private</a></td>
</tr>
<tr>
<td align="center"><a href="#-omniroute-in-action">🎬 In Action</a></td>
<td align="center"><a href="#-dashboard-screenshots">📸 Screenshots</a></td>
<td align="center"><a href="#-support--community">📧 Support</a></td>
</tr>
</table>
</div>
<div align="center">
<b>🌐 In 43 languages</b>
<br/><br/>
<a href="README.md"><img src="docs/assets/flags/us.svg" width="30" alt="English (en)" title="English (en)"></a>
<a href="docs/i18n/pt-BR/README.md"><img src="docs/assets/flags/br.svg" width="30" alt="Português — Brasil (pt-BR)" title="Português — Brasil (pt-BR)"></a>
<a href="docs/i18n/pt/README.md"><img src="docs/assets/flags/pt.svg" width="30" alt="Português (pt)" title="Português (pt)"></a>
<a href="docs/i18n/es/README.md"><img src="docs/assets/flags/es.svg" width="30" alt="Español (es)" title="Español (es)"></a>
<a href="docs/i18n/fr/README.md"><img src="docs/assets/flags/fr.svg" width="30" alt="Français (fr)" title="Français (fr)"></a>
<a href="docs/i18n/it/README.md"><img src="docs/assets/flags/it.svg" width="30" alt="Italiano (it)" title="Italiano (it)"></a>
<a href="docs/i18n/de/README.md"><img src="docs/assets/flags/de.svg" width="30" alt="Deutsch (de)" title="Deutsch (de)"></a>
<a href="docs/i18n/nl/README.md"><img src="docs/assets/flags/nl.svg" width="30" alt="Nederlands (nl)" title="Nederlands (nl)"></a>
<a href="docs/i18n/ru/README.md"><img src="docs/assets/flags/ru.svg" width="30" alt="Русский (ru)" title="Русский (ru)"></a>
<a href="docs/i18n/uk-UA/README.md"><img src="docs/assets/flags/ua.svg" width="30" alt="Українська (uk-UA)" title="Українська (uk-UA)"></a>
<a href="docs/i18n/pl/README.md"><img src="docs/assets/flags/pl.svg" width="30" alt="Polski (pl)" title="Polski (pl)"></a>
<a href="docs/i18n/cs/README.md"><img src="docs/assets/flags/cz.svg" width="30" alt="Čeština (cs)" title="Čeština (cs)"></a>
<a href="docs/i18n/sk/README.md"><img src="docs/assets/flags/sk.svg" width="30" alt="Slovenčina (sk)" title="Slovenčina (sk)"></a>
<a href="docs/i18n/ro/README.md"><img src="docs/assets/flags/ro.svg" width="30" alt="Română (ro)" title="Română (ro)"></a>
<a href="docs/i18n/hu/README.md"><img src="docs/assets/flags/hu.svg" width="30" alt="Magyar (hu)" title="Magyar (hu)"></a>
<a href="docs/i18n/bg/README.md"><img src="docs/assets/flags/bg.svg" width="30" alt="Български (bg)" title="Български (bg)"></a>
<a href="docs/i18n/da/README.md"><img src="docs/assets/flags/dk.svg" width="30" alt="Dansk (da)" title="Dansk (da)"></a>
<a href="docs/i18n/fi/README.md"><img src="docs/assets/flags/fi.svg" width="30" alt="Suomi (fi)" title="Suomi (fi)"></a>
<a href="docs/i18n/no/README.md"><img src="docs/assets/flags/no.svg" width="30" alt="Norsk (no)" title="Norsk (no)"></a>
<a href="docs/i18n/sv/README.md"><img src="docs/assets/flags/se.svg" width="30" alt="Svenska (sv)" title="Svenska (sv)"></a>
<a href="docs/i18n/zh-CN/README.md"><img src="docs/assets/flags/cn.svg" width="30" alt="中文 — 简体 (zh-CN)" title="中文 — 简体 (zh-CN)"></a>
<a href="docs/i18n/zh-TW/README.md"><img src="docs/assets/flags/tw.svg" width="30" alt="中文 — 繁體 (zh-TW)" title="中文 — 繁體 (zh-TW)"></a>
<a href="docs/i18n/ja/README.md"><img src="docs/assets/flags/jp.svg" width="30" alt="日本語 (ja)" title="日本語 (ja)"></a>
<a href="docs/i18n/ko/README.md"><img src="docs/assets/flags/kr.svg" width="30" alt="한국어 (ko)" title="한국어 (ko)"></a>
<a href="docs/i18n/th/README.What people ask about OmniRoute
What is diegosouzapw/OmniRoute?
+
diegosouzapw/OmniRoute is subagents for the Claude AI ecosystem. Never stop coding. Free MIT AI gateway: one endpoint, 290+ providers (90+ free), 500+ models — Kimi, Claude, GPT, OpenAI, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 500+ contributors It has 32.3k GitHub stars and was last updated today.
How do I install OmniRoute?
+
You can install OmniRoute by cloning the repository (https://github.com/diegosouzapw/OmniRoute) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is diegosouzapw/OmniRoute safe to use?
+
Our security agent has analyzed diegosouzapw/OmniRoute and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains diegosouzapw/OmniRoute?
+
diegosouzapw/OmniRoute is maintained by diegosouzapw. The last recorded GitHub activity is from today, with 251 open issues.
Are there alternatives to OmniRoute?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy OmniRoute to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/diegosouzapw-omniroute)<a href="https://claudewave.com/repo/diegosouzapw-omniroute"><img src="https://claudewave.com/api/badge/diegosouzapw-omniroute" alt="Featured on ClaudeWave: diegosouzapw/OmniRoute" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.